How we use Reinforcement Learning to solve the abbey of the crime
summary
Describes using reinforcement learning to train an AI to play and complete the 1987 8-bit game The Abbey of the Crime, a hugely complex 2.5D RPG. Explains the AI system design and the end-to-end training pipelines built with Kubeflow and Google Cloud products to run and manage the learning process.
AI-written summary · about
related talks
47mHow we use Reinforcement Learning (...)
02mDesigning a Video Game AI
24mDesigning a Video Game AI with Reinforcement Learning
31mDesigning game AI with reinforcement learning
56mCan I do AI?
37mHow I trained an AI Model to Beat the 1990's Arcade Game Double Dragon
28mDeep Reinforcement Learning: theory, intuition, code
30mReinforcement Learning - ChatGPT, Playing Games & More